University of Cambridge > Talks.cam > Computer Laboratory Opera Group Seminars > Run-time behavioural models for error detection, fault diagnosis, and self-recovery

Run-time behavioural models for error detection, fault diagnosis, and self-recovery

Download to your calendar using vCal

If you have a question about this talk, please contact Tom Playford .

Existing systems-management tools are essentially a plumbing infrastructure: they collect data and present it to administrators, typically with an API to allow administrators to code scripts for automated analysis. Plumbing is the easy part; analysis is the hard part; this talk will describe our research on creating effective run-time behavioural models of log and metric data, together with work on how to then use that data for fault localisation and diagnosis, leading to self-recovering systems. Given the large costs of running enterprise information systems ($100 billion annually in the US alone; US Bureau of Labor Statistics), our research is expected to result in very significant cost reductions.

This talk is part of the Computer Laboratory Opera Group Seminars series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity